Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 601 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0271. Min Range: -3.0271

Max Act: 3.0271. Min Act: -0.0000

Data Index: 847587 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.7633. Min Act: -0.0000

Data Index: 626761 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.7601. Min Act: -0.0000

Data Index: 19191 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.4588. Min Act: -0.0000

Data Index: 886422 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.5662. Min Act: -0.0000

Data Index: 1081969 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.7122. Min Act: -0.0000

Data Index: 773162 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.4298. Min Act: -0.0000

Data Index: 709954 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.5229. Min Act: -0.0000

Data Index: 248657 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.2171. Min Act: -0.0000

Data Index: 474249 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.4692. Min Act: -0.0000

Data Index: 484349 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.1950. Min Act: -0.0000

Data Index: 1183664 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.2503. Min Act: -0.0000

Data Index: 323735 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.3610. Min Act: -0.0000

Data Index: 413688 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.0810. Min Act: -0.0000

Data Index: 1183889 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.2839. Min Act: -0.0000

Data Index: 814520 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.1512. Min Act: -0.0000

Data Index: 53800 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.0225. Min Act: -0.0000

Data Index: 704805 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 3.0271. Min Range: -3.0271

Max Act: 2.1039. Min Act: -0.0000

Data Index: 504470 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 3.0271. Min Range: -3.0271

Max Act: 1.9216. Min Act: -0.0000

Data Index: 539488 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 3.0271. Min Range: -3.0271

Max Act: 1.8190. Min Act: -0.0000

Data Index: 418600 (C4 (Web Text))

Max Activating Token Index: 308